Update README.md

README.md

@@ -35,6 +35,7 @@ It achieves the following results on the evaluation set:
 ## Model description
 
 Model: "tf_bert_for_token_classification"
+```
 _________________________________________________________________
  Layer (type)                Output Shape              Param #   
 =================================================================
@@ -49,6 +50,7 @@ Total params: 107,726,601
 Trainable params: 107,726,601
 Non-trainable params: 0
 _________________________________________________________________
+```
 
 ## Intended uses & limitations
 
@@ -62,6 +64,7 @@ This model can be used for named entity recognition tasks. It is trained on [Con
 
 The model is evaluated on [seqeval](https://github.com/chakki-works/seqeval) metric and the result is as follows:
 
+```
 {'LOC': {'precision': 0.9655361050328227,
   'recall': 0.9608056614044638,
   'f1': 0.9631650750341064,
@@ -82,6 +85,7 @@ The model is evaluated on [seqeval](https://github.com/chakki-works/seqeval) met
  'overall_recall': 0.9527095254123191,
  'overall_f1': 0.944996244053084,
  'overall_accuracy': 0.9864013657502796}
+```
 
 ## Training procedure